Triple

T18944002
Position Surface form Disambiguated ID Type / Status
Subject The Suburbans E463459 entity
Predicate starring P1507 FINISHED
Object Tony Guma NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Tony Guma | Statement: [The Suburbans, starring, Tony Guma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tony Guma
Context triple: [The Suburbans, starring, Tony Guma]
  • A. Tony Guma chosen
    Tony Guma is a screenwriter best known for co-writing the 1999 comedy film "The Suburbans."
  • B. Johnny Lovo
    Johnny Lovo is a crime boss character in the 1932 gangster film "Scarface," serving as an early mentor and rival to the ambitious protagonist Tony Camonte.
  • C. Tony Tanti
    Tony Tanti is a former Canadian professional ice hockey forward best known for his high-scoring NHL career in the 1980s, particularly with the Vancouver Canucks.
  • D. Sammy Angott
    Sammy Angott was an American professional boxer and former world lightweight champion known for his crafty, awkward style and victories over several top fighters of his era.
  • E. Phil Gubala
    Phil Gubala is a notable resident associated with the community of Affton, Missouri.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8dcfec90481909e926be9767e5779 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d53e6e0c81908a547e21c4819bac completed April 20, 2026, 7:26 a.m.
Created at: April 10, 2026, 11:59 a.m.